Sample-Efficient Diffusion for Text-To-Speech Synthesis
This work introduces Sample-Efficient Speech Diffusion (SESD), an algorithm for effective speech synthesis in modest data regimes through latent diffusion. It is based on a novel diffusion architecture, that we call U-Audio Transformer (U-AT), that efficiently scales to long sequences and operates in the latent space of a pre-trained audio autoencoder. Conditioned on character-aware language model representations, SESD achieves impressive results despite training on less than 1k hours of speech - far less than current state-of-the-art systems. In fact, it synthesizes more intelligible speech than the state-of-the-art auto-regressive model, VALL-E, while using less than 2% the training data.
Code (1)
Tasks
Language ModelingLanguage ModellingSpeech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
Denoising diffusion probabilistic models (DDPMs) have shown promising performance for speech synthesis. However, a large number of iterative steps are required to achieve high sample quality, which restricts the inferenc…
DenoisingGPUSinging Voice SynthesisSpeech Synthesis+2FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis
Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthes…
DenoisingGPUSpeech Synthesistext-to-speech+3DiffCSS: Diverse and Expressive Conversational Speech Synthesis with Diffusion Models
Conversational speech synthesis (CSS) aims to synthesize both contextually appropriate and expressive speech, and considerable efforts have been made to enhance the understanding of conversational context. However, exist…
DiversityLanguage ModelingLanguage ModellingSpeech SynthesisDiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
Denoising diffusion probabilistic models (DDPMs) are expressive generative models that have been used to solve a variety of speech synthesis problems. However, because of their high sampling costs, DDPMs are difficult to…
DenoisingSpeech Synthesistext-to-speechText to SpeechCM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models
Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, r…
DenoisingSpeech Synthesistext-to-speechText to Speech+1